← ClaudeAtlas

gabe-reviewlisted

Code review — risk pricing, confidence scoring, interactive triage, deferred-item tracking, plan alignment, the cost of NOT fixing each finding.
khujta/gabe-suite · ★ 0 · Code & Development · score 63
Install: claude install-skill khujta/gabe-suite
# Gabe Review — Code Review with Risk Pricing ## Gabe execution contract (E1–E7) This skill runs under the suite execution contract — E1 EVIDENCE · E2 RUN-BEFORE-✅ · E3 NO SILENT DOWNGRADE · E4 REUSE FIRST · E5 STATE SYNC · E6 MISSING ANCHOR = STOP · E7 REPORT WHERE — floors, not ceilings; a skill's own gate may be stricter, never looser. Full text: `../gabe-docs/references/execution-contract.md` (if that file is missing, E6 applies — STOP). ## What this does Review code changes and price every finding — what it costs to fix now, what it costs to ignore, and what you're betting by deferring. Track deferred items across reviews and escalate when the same gap gets kicked down the road. This is NOT a generic checklist review. Every finding gets a **Defer Risk** (consequence + probability) and a **Maturity Gate** (MVP/Enterprise/Scale). The output is a risk matrix with a **Review Confidence Score** that lets humans make informed ship/defer decisions — and an interactive **Triage** loop (fix now / defer / dismiss / skip, per-finding or bulk) to resolve findings on the spot. > **Rendering note.** Output wrapped in bare triple-backtick fences is a spec-meta delimiter — render as plain markdown at runtime (tables render as tables), not monospace code. Tagged fences (```bash, ```diff, etc.) stay fenced. See `../gabe-docs/references/docs-spec.md` § "Runtime output rendering convention". ## Usage / modes | Mode | Target | What happens | |---|---|---| | (no args) | Resolved via K